Graham Mann

Detection of glaucoma progression is crucial to managing patients, permitting individualized care plans and treatment. It is a challenging task requiring the assessment of structural changes to the optic nerve head and functional changes based on visual field testing. Artificial intelligence, especially deep learning techniques, has shown promising results in many applications, including glaucoma diagnosis. This paper proposes a two-stage computational learning pipeline for detecting glaucoma progression using only fundus photographs. In the first stage, a deep learning model takes a time series of fundus photographs as input and outputs a vector of predictions where each element represents the overall rate of change in visual field (VF) sensitivity values for a sector (region) of the optic nerve head (ONH). We implemented two deep learning models—ResNet50 and InceptionResNetV2—for this stage. In the second stage, a binary classifier (weighted logistic regression) takes the predicted vector as input to detect progression. We also propose a novel method for constructing annotated datasets from temporal sequences of clinical fundus photographs and corresponding VF data suitable for machine learning. Each dataset element comprises a temporal sequence of photographs together with a vector-valued label. The label is derived by computing the pointwise linear regression of VF sensitivity values at each VF test location, mapping these locations to eight ONH sectors, and assigning the overall rate of change in each sector to one of the elements of the vector. We used a retrospective clinical dataset with 82 patients collected at multiple timepoints over five years in our experiments. The InceptionResNetV2-based implementation yielded the best performance, achieving detection accuracies of 97.28 ± 1.10 % for unseen test data (i.e., each dataset element is unseen but originates from the same set of patients appearing in the training dataset), and 87.50 ± 0.70 % for test data from unseen patients (training and testing patients are entirely different). The testing throughput was 11.60 ms per patient. These results demonstrate the efficacy of the proposed method for detecting glaucoma progression from fundus photographs.

Optic disc (OD) segmentation from retinal images is crucial for diagnosing, assessing, and tracking the progression of several sight-threatening diseases. This paper presents a deep machine-learning method for semantically segmenting OD from retinal images. The method is named multiscale guided attention network (MSGANet-OD), comprising encoders for extracting multiscale features and decoders for constructing segmentation maps from the extracted features. The decoder also includes a guided attention module that incorporates features related to structural, contextual, and illumination information to segment OD. A custom loss function is proposed to retain the optic disc's geometrical shape (i.e., elliptical) constraint and to alleviate the blood vessels' influence in the overlapping region between the OD and vessels. MSGANet-OD was trained and tested on an in-house clinical color retinal image dataset captured during ophthalmodynamometry as well as on several publicly available color fundus image datasets, e.g., DRISHTI-GS, RIM-ONE-r3, and REFUGE1. Experimental results show that MSGANet-OD achieved superior OD segmentation performance from ophthalmodynamometry images compared to widely used segmentation methods. Our method also achieved competitive results compared to state-of-the-art OD segmentation methods on public datasets. The proposed method can be used in automated systems to quantitatively assess optic nerve head abnormalities (e.g., glaucoma, optic disc neuropathy) and vascular changes in the OD region.

Intracranial pressure (ICP) measurement is vital in managing and treating patients with brain injuries, brain tumors, and other neuro-ophthalmic conditions. Invasive methods have reached a high standard of accuracy but pose multiple risks to patients and require specialized resources. In contrast, non-invasive methods indirectly estimate ICP based on related physiological properties. This paper surveys imaging-based methods that utilize cerebro-ophthalmic anatomy and fluid dynamics. The theoretical basis of each method is presented, including the physiological attributes and imaging modality used. Details of empirical studies are also presented, including subjects (type, population, medical indication, captured anatomies), methodology, and evaluations of ICP estimation accuracy. The pros and cons of each method are presented in terms of complexity, patient acceptability, operating expertise, potential for clinical application, costs, and time. Whilst none of the methods in the survey has to date achieved the reliability and accuracy of invasive methods used clinically, those based on transcranial and orbital ultrasonography and direct retinal imaging demonstrate great promise. Refinements to these methods, including the application of modern deep learning techniques, offer the prospect of non-invasive, clinically acceptable, accurate and automatic measurement of ICP.

Background

Retinal and optic disc images are used to assess changes in the retinal vasculature. These can be changes associated with diseases such as diabetic retinopathy and glaucoma or induced using ophthalmodynamometry to measure arterial and venous pressure. Key steps toward automating the assessment of these changes are the segmentation and classification of the veins and arteries. However, such segmentation and classification are still required to be manually labelled by experts. Such automated labelling is challenging because of the complex morphology, anatomical variations, alterations due to disease and scarcity of labelled data for algorithm development. We present a deep machine learning solution called the multiscale guided attention network for retinal artery and vein segmentation and classification (MSGANet-RAV).

Methods

MSGANet-RAV was developed and tested on 383 colour clinical optic disc images from LEI-CENTRAL, constructed in-house and 40 colour fundus images from the AV-DRIVE public dataset. The datasets have a mean optic disc occupancy per image of 60.6% and 2.18%, respectively. MSGANet-RAV is a U-shaped encoder-decoder network, where the encoder extracts multiscale features, and the decoder includes a sequence of self-attention modules. The self-attention modules explore, guide and incorporate vessel-specific structural and contextual feature information to segment and classify central optic disc and retinal vessel pixels.

Results

MSGANet-RAV achieved a pixel classification accuracy of 93.15%, sensitivity of 92.19%, and specificity of 94.13% on LEI-CENTRAL, outperforming several reference models. It similarly performed highly on AV-DRIVE with an accuracy, sensitivity and specificity of 95.48%, 93.59% and 97.27%, respectively.

Conclusion

The results show the efficacy of MSGANet-RAV for identifying central optic disc and retinal arteries and veins. The method can be used in automated systems designed to assess vascular changes in retinal and optic disc images quantitatively.

The need for software applications that can assist with mental disorders has never been greater. Individuals suffering from mental illnesses often avoid consultation with a psychotherapist, because they do not realize the need, or because they cannot or will not face the social and economic consequences, which can be severe. Between ideal treatment by a human therapist and self-help websites lies the possibility of a helpful interaction with a language-using computer. A model of empathic response planning for sentence generation in a forthcoming automated psychotherapist is described here. The model combines emotional state tracking, contextual information from the patient’s history and continuously updated therapeutic goals to form suitable conceptual graphs that may then be realized as suitable textual sentences.

The need for software applications that can assist with mental disorders has never been greater. Individuals suffering from mental illnesses often avoid consultation with a psychotherapist, because they do not realize the need, or because they cannot or will not face the social and economic consequences, which can be severe. Between ideal treatment by a human therapist and self-help websites lies the possibility of a helpful interaction with a language-using computer. A practical model of empathic response planning for sentence generation in a forthcoming automated psychotherapist is described here. The model combines emotional state tracking, contextual information from the patient’s history and continuously updated therapeutic goals to form suitable conceptual graphs that may then be realized as suitable textual sentences.

This paper proposes an architecture that explores a gap in the spectrum of existing strategies for robot control mode switching in adjustable autonomy. In situations where the environment is reasonably known and/or predictable, pre-planning these control changes could relieve robot operators of the additional task of deciding when and how to switch. Such a strategy provides a clear division of labour between the automation and the human operator(s) before the job even begins, allowing for individual responsibilities to be known ahead of time, limiting confusion and allowing rest breaks to be planned. Assigned Responsibility is a new form of adjustable autonomy-based teleoperation that allows the selective inclusion of automated control elements at key stages of a robot operation plan’s execution. Progression through these stages is controlled by automatic goal accomplishment tracking. An implementation is evaluated through engineering tests and a usability study, demonstrating the viability of this approach and offering insight into its potential applications.

Electronic discovery (also written as e-discovery or eDiscovery) and digital forensics are processes in which electronic data is sought, located, secured, and processed with the expectation that it may be used as evidence in legal proceedings. Electronic evidence plays a fundamental role in many aspects of litigation (Stanfield, 2009). However, both eDiscovery and digital forensic approaches that rely on the creation of an index as part of their processing are struggling to cope with the huge increases in hard disk storage capacity. This paper introduces a novel technology that meets the existing and future data volume challenges faced by practitioners in these areas. The technology also addresses the concerns of those responsible for maintaining corporate networks as it does not require installation of ‘agents’ nor does it have any significant impact on network bandwidth during the search and collection process, even when this involves many computers. The technology is the embodiment of a patented process that opens the way for the development of new functionality, such as the detection of malware, compliance with corporate Information Technology (IT) policies and IT auditing. The technology introduced in this paper has been incorporated into a commercial tool called ISEEK that has already been successfully deployed in a variety of environments.

There are good reasons to believe that small (< 5kg), highly manoeuvrable rotorcraft may be valuable to human explorers on Mars. They could be used for scouting, aerial photography, maintenance inspection, hoisting antenna or guy wires, locating science targets and rapid transportation of small tools or regolith samples. Low atmospheric pressures and temperatures near the Martian surface present severe challenges to the design of rotorcraft. To provide sufficient lift, even allowing for lower gravitational acceleration (3.71m/s2), rotors need to be larger and turn faster than their terrestrial counterparts, thus imposing high mechanical stresses. This, combined with poor battery efficiency at low temperatures, could impose serious restrictions on the endurance of such aircraft. Extremely fine and abrasive particulate matter would also be problematic for reliable functioning of any exposed bearings, sensors and cameras. In this paper we study the use of both conventional and modified low pressure propellers for the use in a small quadrotor at low pressures. We modelled the rotors computationally and our simulations show the need for a thrust of approximately 5N per motor for a 4kg quadrotor at Mars. Blade element theory calculations have suggested that it is possible to meet these requirements. As a baseline, conventional propeller designs were tested in a vacuum chamber down to 6 mbar. As the pressure was reduced the thrust dropped significantly from approximately 6N to 0.05N. However, the power consumption also dropped from 120W to 16W due to the much lower drag on the propeller. Tests on propellers based on our simulations also demonstrated a decrease in thrust. While this system is not yet optimised, it demonstrated only a 60% decrease in thrust which compares favourably with conventional propellers, with a 40% reduction in power consumption. This suggests that correctly optimised propellers may indeed be able to be used as propulsion for lightweight multirotor aircraft on Mars. Since our vacuum chamber tests are complicated by ground effects and limited freedom to move, we intend to drop a 4kg automated test vehicle from a balloon at 120,000 feet, where atmospheric conditions approximate those at Mars, and record performance data onboard during programmed manoeuvres. The decent of the rotorcraft could also be used to correct the results for the greater acceleration due to gravity near Earth.

Confronting the expected rise of dementia as a major health care problem raises many questions about the best ways to adapt the health system to deal with it. To the extent that intelligent assistive technologies can help, there seems to be value in comforting fabric artifacts enhanced by electronic games and activities designed to support, engage and entertain people with dementia. Local cottage industries which now support the creation of textile crafts should be empowered to scale up to meet the growing demand for such products. New design concepts are required to accomplish this in the face of rising costs and limited resources. This paper proposes a four-step design process that meets this need, and provides practical suggestions about how it could be applied in this context. A number of examples are included.